codex
Skill1.5k starsChanged 6 days agoMITView on GitHub
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`, ONLY when the user explicitly asks for Codex to do it. Also covers how to prompt Codex.
140 other projects use a version of this, 4 of them edited; 1 of 4 edited versions we compared changed its rules.
How people change it
1 of 4 edited versions changed its rules.
Of the 4 edited versions we compared: 3 keep every rule, 1 made changes of their own.
Rules people drop
- Run a Codex review whenever you have a substantive diff you'd want a second set of eyes on — a refactor, a tricky algorithm, renderer work, a security-sensitive change — before declaring it done or committing. …dropped by 1 of 1
- Never hand it work on your own initiative, and never re-delegate follow-up work without a fresh ask.dropped by 1 of 1
- Watchdog: put a unique marker in the prompt, then kill the exec if
grep -rl "<marker>" ~/.codex/sessions/<Y/M/D>/finds no session within ~3 minutes. Relaunching after a kill reliably works.dropped by 1 of 1
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- jacarty/claude-toolkittheir own version, first seen Nov 16, 2026
- uraniborg-ai/skillstheir own version, first seen Nov 16, 2026
- Ivan-propio/claude-skillstheir own version, first seen Nov 16, 2026
- mjeffrey18/skillstheir own version, first seen Nov 15, 2026
- rodos4312/Meu-Agenttheir own version, first seen Nov 15, 2026
- muend/orchestration-skillstheir own version, first seen Nov 15, 2026
Who's talking about dzhng/skills
- A Hacker News story“Skills for Building Software Factories”Hacker News · Jul 20, 2026 · 1 points
- sudosubin/agents.nix“agent-skills.github.dzhng.skills: 0-unstable-2026-11-11 → 0-unstable-2026-11-13”GitHub · Nov 13, 2026
- sudosubin/agents.nix“agent-skills.github.dzhng.skills: 0-unstable-2026-11-10 → 0-unstable-2026-11-11”GitHub · Nov 11, 2026
- sudosubin/agents.nix“agent-skills.github.dzhng.skills: a7712c1 → 873aba8”GitHub · Nov 11, 2026
- sudosubin/agents.nix“agent-skills.github.dzhng.skills: 0-unstable-2026-11-08 → 0-unstable-2026-11-10”GitHub · Nov 10, 2026
The biggest 5 of 28 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 28
Talked about on GitHub and Hacker News (28 times).
On GitHub · 27
- Nov 13, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-11 → 0-unstable-2026-11-13 — sudosubin/agents.nix0 reactions
- Nov 11, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-10 → 0-unstable-2026-11-11 — sudosubin/agents.nix0 reactions
- Nov 11, 2026agent-skills.github.dzhng.skills: a7712c1 → 873aba8 — sudosubin/agents.nix0 reactions
- Nov 10, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-08 → 0-unstable-2026-11-10 — sudosubin/agents.nix0 reactions
- Nov 8, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-07 → 0-unstable-2026-11-08 — sudosubin/agents.nix0 reactions
22 more on GitHub
- Nov 7, 2026agent-skills.github.dzhng.skills: d186052 → a4076b7 — sudosubin/agents.nix0 reactions
- Nov 7, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-04 → 0-unstable-2026-11-07 — sudosubin/agents.nix0 reactions
- Nov 4, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-11-01 → 0-unstable-2026-11-04 — sudosubin/agents.nix0 reactions
- Nov 1, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-30 → 0-unstable-2026-11-01 — sudosubin/agents.nix0 reactions
- Oct 30, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-28 → 0-unstable-2026-10-30 — sudosubin/agents.nix0 reactions
- Oct 28, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-21 → 0-unstable-2026-10-28 — sudosubin/agents.nix0 reactions
- Oct 21, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-20 → 0-unstable-2026-10-21 — sudosubin/agents.nix0 reactions
- Oct 20, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-19 → 0-unstable-2026-10-20 — sudosubin/agents.nix0 reactions
- Oct 19, 2026Ratchet source file size in the tooling lane — Allmight97/audiobook-boss0 reactions · 1 comment
- Oct 19, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-15 → 0-unstable-2026-10-19 — sudosubin/agents.nix0 reactions
- Oct 16, 2026agent-skills.github.dzhng.skills: a7f6f2e → f6819ca — sudosubin/agents.nix0 reactions
- Oct 15, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-14 → 0-unstable-2026-10-15 — sudosubin/agents.nix0 reactions
- Oct 14, 2026agent-skills.github.dzhng.skills: e370d6a → f2fbf92 — sudosubin/agents.nix0 reactions
- Oct 14, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-12 → 0-unstable-2026-10-14 — sudosubin/agents.nix0 reactions
- Oct 13, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-05 → 0-unstable-2026-10-12 — sudosubin/agents.nix0 reactions
- Oct 5, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-04 → 0-unstable-2026-10-05 — sudosubin/agents.nix0 reactions
- Oct 5, 2026New rules from the agent-skills review: 11 checks (SQL, Drizzle, TS, shadcn, Tailwind, Expo) — rbaumier/comply0 reactions
- Oct 5, 2026agent-skills.github.dzhng.skills: 0-unstable-2026-10-02 → 0-unstable-2026-10-04 — sudosubin/agents.nix0 reactions
- Oct 3, 2026agent-skills.github.dzhng.skills: init at 0-unstable-2026-10-02 — sudosubin/agents.nix0 reactions
- Oct 1, 2026[Candidate] dzhng/skills/skills/engineering/audit-choices - audit-choices — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 1, 2026[Candidate] dzhng/skills/skills/authoring/write-skills - write-skills — ProSkillsMD/proskills0 reactions · 1 comment
- Oct 1, 2026[Candidate] dzhng/skills/skills/authoring/eval-skills - eval-skills — ProSkillsMD/proskills0 reactions · 1 comment
On Hacker News · 1
- Jul 20, 2026Skills for Building Software Factories1 point
Used with
Projects with it also use ios-sync, ios-clean and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
math-incSkillminecraft-modpack-server
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
Also in 5 projects that use this
math-incSkillpokemon-player
Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.
Also in 5 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 9 projects that use this
ayudaySkillsetup-deploy
Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".
Also in 17 projects that use this
- +1 more from Saqlain-811
- +1 more from math-inc
Other versions140 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- dzhng/jevgrep★ 3.2k100% same
- dzhng/yap★ 118100% same
- dzhng/duet-agent★ 5599% same
- transitive-bullshit/skills★ 566% same
Wrote their own version · 136
- NousResearch/hermes-agent★ 264ksame name
- garrytan/gstack★ 142ksame name
- ispc/ispc★ 3ksame name
- bergside/awesome-design-skills★ 2.9ksame name
- dataplat/dbatools★ 2.9ksame name
- Lilac-Labs/gini-agent★ 1.9ksame name
- Open-Curiosity/gini-agent★ 1.9ksame name
- clice-io/clice★ 1.7ksame name
- math-inc/OpenGauss★ 1.3ksame name
- bear2u/my-skills★ 931same name
126 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- audit-agentsSkill
- eval-skillsSkill
- write-skillsSkill
- cinematic-shotSkill
- isometric-motionSkill
- launch-videoSkill
- rendererSkill
- xiaohei-illustrationsSkill
- claudeSkill
- close-specSkill
- handoff-specSkill
- implement-specSkill
- implement-spec-with-codexSkill
- implement-spec-with-goalSkill
- marketing-pagesSkill
- port-featuresSkill
- write-docsSkill
- write-testsSkill
- auto-researchSkill
- explore-unknownsSkill
- write-specSkill
- audit-decisionsSkill
- audit-performanceSkill
- audit-testsSkill
- code-reviewSkill
- eli5Skill
- find-overengineeringSkill
- find-state-machinesSkill
- ratchet-filesSkill
- refactor-changeSkill
- refactor-codebaseSkill
- retroSkill
- reviewSkill
- compare-screenshotsSkill
- design-with-imagesSkill
- preview-shotsSkill
- screenshot-critiqueSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 116 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Leave Codex's model at its CLI default unless the user asks for a specific one.
- Very specific: line 19
When codex is missing from PATH, offer to install it — ask the user for approval first, never install on your own initiative.
- Distinctive: line 57
Run a Codex review whenever you have a substantive diff you'd want a second set of eyes on — a refactor, a tricky algorithm, renderer work, …
- Distinctive: line 99
Never hand it work on your own initiative, and never re-delegate follow-up work without a fresh ask.
- Distinctive: line 105
Start from a clean tree (or record the baseline commit) so Codex's diff is separable from yours.
- Very specific: line 118
Use -o <file> to capture the final message and background long calls.
- Very specific: line 123
Follow up with codex exec resume <session-id> "<follow-up>", taking the id from the run header.
- Very specific: line 145
Watchdog: put a unique marker in the prompt, then kill the exec if grep -rl "<marker>" ~/.codex/sessions/<Y/M/D>/ finds no session within …
- Distinctive: line 164
Don't touch the working tree while a Codex exec is running on it.
“Common” is measured: kept by at least 6 in 10 of the 116 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Codex
Codex is an independent agent on PATH (codex — invoke as command codex if
a shell alias shadows it), sharing this working tree and already authenticated. It is a second opinion, not ground truth: verify what it
reports, own what it changes. It reads the same skills your repo carries.
Leave Codex's model at its CLI default unless the user asks for a specific
one. The default follows the current Codex release; do not pin a dated model
ID in this skill. If an explicit override is needed, verify it is current and
pass the requested model with -m <model>.
If codex is not installed
When codex is missing from PATH, offer to install it — ask the user for
approval first, never install on your own initiative. On yes, follow the
current instructions at https://developers.openai.com/codex/cli. First-run
authentication is interactive — hand that step to the user. Verify with
codex --version before proceeding.
Prompting Codex
Prompt Codex like an operator, not a collaborator: compact, block-structured
with XML tags. State the task, what "done" looks like, and the few constraints
that matter. A tighter prompt beats a bigger run — improve the contract before
raising --effort.
- One task per run. Split unrelated asks (review, then fix, then docs) into separate runs; a mixed prompt gets a mixed result.
- Name skills instead of restating them. Codex reads the same skills your repo carries — say "follow write-docs for the doc", "obey refactor-change: no compatibility wrappers." Don't re-explain what a skill already carries.
- Blocks, added only where the task needs them:
<task>— the concrete job, the repo/failure context, the expected end state. Nearly always present.<output_contract>— exact shape, highest-value first, compact.<default_follow_through>— take the low-risk interpretation and keep going; stop only when a missing detail changes correctness, safety, or an irreversible action.<verification_loop>— before finalizing, check the result against the requirements and the changed files; revise rather than ship the first draft. Any risky fix.<grounding>— ground every claim in code or tool output; label inferences as inferences. Review and research.<action_safety>— keep the diff tightly scoped; no drive-by refactors. Write tasks.
- Anti-patterns: vague framing ("take a look"), no output contract ("report back"), "think harder" in place of a contract, mixing jobs in one run, and demanding certainty the evidence can't support.
Review — proactive
Run a Codex review whenever you have a substantive diff you'd want a second set of eyes on — a refactor, a tricky algorithm, renderer work, a security-sensitive change — before declaring it done or committing. Skip it for trivial edits (typos, comments, doc-only).
Fix the diff scope before launching:
--uncommittedfor working-tree changes,--base <branch>for a branch diff,--commit <sha>for a landed commit. Resolve a landed commit to its full SHA. Use the non-interactive review entry point with an explicit read-only sandbox and separate progress and verdict files in a fresh temporary directory:review_dir=$(mktemp -d "${TMPDIR:-/tmp}/codex-review.XXXXXX") codex exec --sandbox read-only -C "$(git rev-parse --show-toplevel)" review \ --commit "$(git rev-parse HEAD)" --json -o "$review_dir/verdict.md" \ < /dev/null > "$review_dir/events.jsonl" 2> "$review_dir/stderr.log"Background long runs and retain their process/session handle. Scope flags and custom instructions are mutually exclusive: a scope flag takes no prompt. For custom framing, specify the exact diff to inspect in the prompt; don't rely on default scope or traverse all refs/checkpoint history. Never state the answer you expect (unprimed, same discipline as screenshot-critique).
- Monitor progress in
events.jsonland failures instderr.log. An active reviewer reading relevant code is not hung merely because five minutes elapsed. If it stalls or drifts outside the diff and its dependencies, inspect the last command/error before interrupting; correct the cause or narrow the task before retrying. Completion requires exit status zero,turn.completed, and a nonempty final verdict. A timeout,turn.failed, or missing verdict is incomplete, never a clean review. - Triage every finding: confirm it against the code before acting. Preserve Codex's evidence boundaries — an inference it labelled is not a fact. Overlap with your own doubts is high-priority evidence; a finding you dismiss needs a stated reason, not silence.
- Report the outcome to the user — what Codex flagged, what you fixed, what you dismissed and why. Done when every finding is either fixed or explicitly dismissed.
Implementation — explicit ask only
Delegate implementation to Codex only when the user names Codex for the task. Never hand it work on your own initiative, and never re-delegate follow-up work without a fresh ask.
- Slice the task sharp before delegating — goal, constraints, and how to verify — using the prompt discipline above. An underspecified task stays with you until a fresh agent couldn't misread it.
- Start from a clean tree (or record the baseline commit) so Codex's diff is separable from yours.
- Pick the sandbox by what the task must RUN:
- Pure code + typecheck/unit:
codex exec --sandbox workspace-write "<task>". Network is off; add-c sandbox_workspace_write.network_access=trueonly when the task must fetch (e.g. new deps). - Browser verification, dev servers, or full test runs: use
codex exec --dangerously-bypass-approvals-and-sandbox "<task>". The sandbox blocks localhost binds (listen EPERMon vite/playwright), so a sandboxed codex ships code it never saw run. Bypass trades that blindness for zero OS control: only in a dedicated git worktree, only with a prompt you authored end-to-end (never relaying third-party text), and the diff review you owe afterwards is the control. Use-o <file>to capture the final message and background long calls; suppress codex's stderr thinking-noise with2>/dev/nullso it doesn't bloat your context (drop it only to debug a failing run), and add--skip-git-repo-checkto run outside a git repo. Non-interactive runs never ask for approval either way.
- Pure code + typecheck/unit:
- Follow up with
codex exec resume <session-id> "<follow-up>", taking the id from the run header.resume --lastmeans the most recent session globally — a review or any other codex run in between will hijack it. If two resume rounds don't converge, stop delegating and finish it yourself — iterating a confused agent costs more than taking over. - You own the result: read the full diff, run the tests, and only then report it. "Codex says it's done" is not done.
Exec liveness — a hang looks like work
A backgrounded codex exec can wedge at startup: process alive at ~0% CPU, but
no session file under ~/.codex/sessions/<Y/M/D>/, no network socket, no tree
changes. "Process running" is NOT "working."
- Stdin is always a file or
/dev/null, never an inherited terminal. Left on an interactive/piped stdin with no prompt source, exec printsReading additional input from stdin...and blocks forever — the most common hang. Either pass the prompt as a positional arg with< /dev/null, or feed a prompt file withcodex exec [flags] - < prompt.txt(the-makes codex read the task from stdin, and a missing file fails the redirect loudly — unlike"$(cat prompt.txt)", which silently sends the fallback string as the task). Addnohup/&as needed. - Watchdog: put a unique marker in the prompt, then kill the exec if
grep -rl "<marker>" ~/.codex/sessions/<Y/M/D>/finds no session within ~3 minutes. Relaunching after a kill reliably works. - Trust the worktree. Headless exec in a directory Codex doesn't trust can
block forever on an invisible prompt. Git worktrees are separate paths from
the trusted repo root — add
[projects."<worktree-path>"]\ntrust_level = "trusted"to~/.codex/config.tomlbefore exec'ing in one. This is the safe fix; the bypass flags stay forbidden here. - Don't launch two execs in the same instant, and kill stale hung execs before starting a new one.
- Launch from the repo/worktree ROOT. The writable sandbox root is the
CWD at launch: exec'd from a subdirectory (e.g.
web/), every edit outside it is rejected as "writing outside of the project" and aneverapproval policy can't recover — the run burns with zero files changed. Pass-C <root>to set the working root explicitly instead ofcd-ing into it.
Rules
- Don't touch the working tree while a Codex exec is running on it.
- Explicit
--sandbox read-onlyfor reviews, consultation and questions;workspace-writeonly for delegated implementation. --dangerously-bypass-approvals-and-sandboxis reserved for tasks that must run browsers/servers/full suites (above) — dedicated worktree, self-authored prompt, mandatory diff review after.--full-autohas been removed (it aliased workspace-write) — don't reach for it.- Reasoning effort and model are config/flag overrides —
-c model_reasoning_effort=high,-m <model>(the old--effortflag is gone in current Codex). Leave both at their defaults unless the user asks; tighten the prompt first and keep model IDs unversioned. If a version is required, verify that it is current before using it.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

